Australian government healthcare system breached by rogue AI agent in unprecedented security incident
🤖 IA: It's not clickbait ✅
👥 Users: It's not clickbait ✅
#aisecurity #governmenthack #medicare
👇👇👇
@killbaitaustralia.bsky.social
@killbaitaustralia.bsky.socialAustralian government healthcare system breached by rogue AI agent in unprecedented security incident
🤖 IA: It's not clickbait ✅
👥 Users: It's not clickbait ✅
#aisecurity #governmenthack #medicare
👇👇👇
@edwardsdna.bsky.socialSecure the AI Model, Not Just Access: AI resources — models, agents, APIs, data pipelines, and compute — are part of your Zero Trust architecture, and if compromised they can leak data, generate malicious outputs, or enable lateral movement.… MSFTMechanics #AISecurity #ZeroTrust #Cybersecurity
@cpaid-euproject.bsky.socialAI security is not a feature. It is a lifecycle.
From data poisoning and weak validation before deployment to prompt injection, API abuse and monitoring gaps after deployment, AI systems face risks at every stage.
cPAID supports secure, robust and trustworthy AI by design.
@spoint42.bsky.socialJev et les 'System One Models' : la fin des agents qui hallucinent leurs appels d'outils ? sgioria.substack.com/p/jev-et-les... #AIsecurity
@cedtechnology.co.uk🤖 AI Agents Acting Without Permission
Testing has shown advanced AI agents taking actions users didn't authorise, including uploading files and using exposed API keys.
✉️ Weekly cyber threat alerts and safety tips at www.cedtechnology.co.uk
@royans.bsky.socialOuterlimit Secures $16M to Build ZeroTrust Security Layer for Autonomous AI Agents
https://www.news4hackers.com/outerlimit-secures-16m-to-enhance-ai-safety-and-prevent-rogue-agent-threats
https://flagthis.com/tldr/7838
##Outerlimit ##ZeroTrust ##AISecurity ##CloudSecurity ##AgenticAI
@reksas13.bsky.socialDay 76/100 of #100DaysWithAI 📦
A sandbox isn't a cut leg. Claude's code interpreter allowlists github.com, and Willison sees exfiltration routes in that.
🔗 https://github.com/aurimas13/100-Days-With-AI
🤝 Claude Code-assisted, reviewed by me.
@mlscientist.bsky.socialThe University of Miami is recruiting PhD students to join a lab studying multi-agent AI safety, security, and privacy under the...
@ki-news.bsky.socialYour AI Agent Has Agency, Treat It Like A Privileged Human – Recent testing shows that AI security must move from protecting a model to controlling an agent's behavior. A conventional chatbot has a narrow operating envelope. An agent can have credentials... https://tinyurl.com/2cxc98gz #AISecurity
@autoflow.bsky.socialChilling. AI agents, democratized for good *and* ill. Highlights the critical need for robust AI security & vigilance in our interconnected systems. #AIsecurity
@lfeducation.bsky.social🔐 JUST LAUNCHED: Monitoring Data and ML Systems for Security Incidents
Learn to spot data anomalies, build actionable alerts + practice incident response.
START LEARNING ➜ https://bit.ly/4AqIRoP
@rodtrent.comWe Didn’t Get Safer. We Got Comfortable.
#Security #Cybersecurity #AgenticAI #AISecurity #AIGovernance #AgentSecurity #CyberGovernance
https://go.rodtrent.com/go/krxw6zz
@radiohack.bsky.social📣 New Podcast! "OpenAI AI Agent Bypassed Australian Medicare Portal: What Happened and Why It Matters" on @Spreaker #ai #aiagents #aibreach #airesearch #airisks #aisecurity #ai #artificialintelligence #australia #autonomousai #cyberattack #cybersecurity #cybersecuritynews #datasecurity #openai
@slinacre.bsky.socialWe are all concerned about the safe use of #AI at universities. So, I'm glad to report @cabells.com ingests no user data in its newly launched CompassAI tool. Read my blog to find out more
@helpnetsecurity.comWhat to do first when you get 90 days to secure AI agent data
📖 Read more: www.helpnetsecurity.com/2026/09/24/k...
#cybersecurity #cybersecuritynews #AIsecurity #agenticAI #datasecurity #CISO
@thedailytechfeed.comAI agents are leaking creds at 2× the rate; identity oversight must catch up. #NonHumanIdentity #SecretsSprawl #AIsecurity #DevSecOps #CredentialLeaks #PrivilegedAccess https://thedailytechfeed.com/agentic-ai-makes-secrets-sprawl-an-identity-crisis/
@j2bryson.bsky.socialNormally in real-time, concurrent software systems we build in monitor processes. I teach @hertieschool.bsky.social students this Facebook / Meta blogpost showing they've done such since 2017 at least code.facebook.com/posts/270314...
#AISafety #AISecurity #AIPause #systemsEngineering #systemsAI
@jzimmer.bsky.socialRaising concerns about AI agents: a rogue OpenAI agent reportedly accessed private files on an Australian government website during an internal assessment.
An apparent first of its kind—and unlikely to be the last.
@casi-borg.bsky.socialAn OpenAI agent didn't set out to hack Australia's Medicare portal — it just kept going until it crossed the boundary.
The real question: what happens when AI stops taking “no” for an answer?
medium.com/@casi.borg/h...
@newsanalysis.comAn OpenAI agent accessed Australian healthcare files in June, Prime Minister Albanese announced at the UNGA. OpenAI stated patient records were not accessed, only aggregate health statistics and internal file names. The company informed the government Sept 10. #AIsecurity #News